An Analysis of the Walking Environmental Factors Affecting the Stress of Pedestrians for Route Recommendation

Walking is an easy exercise for maintaining health, although there are several environmental factors, such as road congestion or slopes, which are stressful for pedestrians, especially elders. Therefore, a pedestrian navigation system is required to recommend a less stressful route for a user by estimating such environmental factors. Towards realizing such a system, we firstly collect vital sign, spatiotemporal and environmental data from pedestrians, and secondly analyze the relation between them, and then propose models for estimating the personal stress of a pedestrian. As our vital sign data, we calculate the stress of each pedestrian from the R-R interval data obtained by a heart rate sensor. Our spatiotemporal data includes the walking speed of pedestrians and road grade calculated from GPS sensor data. We measure the degree of road congestion, as our environmental data, using a laser range finder. Our analysis reveals that the road congestion is an important factor affecting stress in walking. The proposed models based on neural networks employ the road congestion in addition to the vital sign and spatiotemporal data. Experimental results indicate that the road congestion degree is effective and the stress of pedestrians estimated by our models is similar to the real stress.

[1]  Ricardo Gutierrez-Osuna,et al.  Using Heart Rate Monitors to Detect Mental Stress , 2009, 2009 Sixth International Workshop on Wearable and Implantable Body Sensor Networks.

[2]  Feng Xiao,et al.  Heart Rate Prediction Model Based on Physical Activities Using Evolutionary Neural Network , 2010, 2010 Fourth International Conference on Genetic and Evolutionary Computing.

[3]  O. G. Okogbaa,et al.  On the investigation of the neurophysiological correlates of knowledge worker mental fatigue using the EEG signal. , 1994, Applied ergonomics.

[4]  B. Kudielka,et al.  Salivary cortisol as a biomarker in stress research , 2009, Psychoneuroendocrinology.

[5]  P. Caminal,et al.  Modeling the dynamics of the heart rate variability by hidden Markov models , 2003, Computers in Cardiology, 2003.

[6]  Keiichi Yasumoto,et al.  Estimating heart rate variation during walking with smartphone , 2013, UbiComp.

[7]  P. Thompson,et al.  ACSM's Guidelines for Exercise Testing and Prescription , 1995 .

[8]  H Selye,et al.  The Stress Syndrome , 1965, [Kango gijutsu] : [Nursing technique].

[9]  Jennifer Healey,et al.  Detecting stress during real-world driving tasks using physiological sensors , 2005, IEEE Transactions on Intelligent Transportation Systems.

[10]  E. H. Heath.  Acsm’s Guidelines for Exercise Testing and Prescription, 7th Edition , 2005 .

[11]  Tamás D. Gedeon,et al.  Artificial Neural Network Classification Models for Stress in Reading , 2012, ICONIP.

[12]  R. Cohen,et al.  Power spectrum analysis of heart rate fluctuation: a quantitative probe of beat-to-beat cardiovascular control. , 1981, Science.

[13]  Shinji Miyake,et al.  Search for Indices to Evaluate Mental Fatigue , 2012 .

[14]  Ikuko Eguchi,et al.  Universal Designed Mobility Support Geographic Information System for All Pedestrians , .

[15]  T Moritani,et al.  Tone-entropy analysis on cardiac recovery after dynamic exercise. , 1997, Journal of applied physiology.

[16]  David Pearlmutter,et al.  The relationship between bioclimatic thermal stress and subjective thermal sensation in pedestrian spaces , 2014, International Journal of Biometeorology.

[17]  Shyamal Patel,et al.  A review of wearable sensors and systems with application in rehabilitation , 2012, Journal of NeuroEngineering and Rehabilitation.